Text Embeddings Inference alternatives for AI agents.

Retrieval and Retrieval-augmented LLMs

Bringing BERT into modernity via both architecture changes and scaling

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

Tantivy is a full-text search engine library inspired by Apache Lucene and written in Rust

Jupyter Notebooks to help you get hands-on with Pinecone vector databases

One delightful Ruby framework for every major AI provider. Build AI agents, chatbots, RAG apps, and multimodal workflows in beautiful, expressive code.

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

Full-text and semantic search on any Postgres

Fast State-of-the-Art Static Embeddings

GraphRAG-rs is a high-performance, state-of-the-art Rust implementation of GraphRAG (Graph-based Retrieval Augmented Generation) that builds knowledge graphs from documents and enables natural language querying with configurable entity extraction and local LLM integration

Postgres with GPUs for ML/AI apps.

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

100+ Chinese Word Vectors 上百种预训练中文词向量

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows